sukhmel

Original thread is also pure gold, bro is going on a rollercoaster from 'vibe coding makes you ×100 faster' ,to 'I hate you for dropping my production DB', to 'I still love Replit even if it dropped my DB', and to 'I don't want to get up in the morning because I can't make vibe coding tool respect code freeze aven with help from its developers'

They seem to end on an optimistic note, but man this is scary to see

It is matrix math, but you get a vector of probabilities out of it and may decide to be adventurous instead of going with the highest probability.

And those patterns, mind you, often include lying and deception. So while I agree that LLMs can't exhibit anything consciously, I also know that they can provide false information. To call it a lie is a stretch, and looks like something one would do if one wants to place blame on LLM for their own fault

That's almost as good as the ones that limit password on the sign-in UI, but not on the sign-up

GPS information from the source

Here, I think you're being downvoted because you missed one of ð in the

✍️ we need PHP interpreter written in Rust, noted

A language usually doesn't become worse with time, at least if the devs do a good job at improving it.

There are cases of new languages that looked better but didn't become mainstream because the ecosystem requires time to grow (and adoption, which creates a vicious cycle because adoption requires ecosystem to already be there)

Just for the sake of being contrary, I know that there are still machines running on punch cards in some army-related places, where not changing anything is mandatory. I wouldn't be surprised if hot-wiring is also still there somewhere, it's just mostly running without changes.

To this I completely agree, a lot of people don't want to use the tools for the benefit of the future colleagues or even self

And the blame has those commit messages. That is beside the fact that most authors may not even work there anymore

This is an interesting finding, but there are two important things to keep in mind: they only reviewed some illnesses, and even there one had better cure rate for longer treatment, this means we need a lot more studies. And another one I will quote from the article you linked:

You should still follow your doctor’s instructions about the length of antibiotic therapy.

If you are feeling better and think that you may not need the entire course, be sure to ask your doctor first.

Considering that many will not be able to ask a doctor on time to stop early, both because it may cost extra and because there's usually a waiting list of who knows how long, it seems unrealistic to expect real change soon.

So, I partially agree with you and will try to spread the info and ask doctors about this, but I think it should rather be seen as a need for more studies. Maybe there already are more, the article is from 2017, but right now I don't have time to search for that.

Thank you for the information

We're below reproduction rate in most parts of the world, and likely will fall below in the rest of the world during this century, so we're already in the 'find out' era :(